© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 728
    Prev
    Next
    INDEX
    Explanations

    lines of code, or data, with a specific format

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ή
    -0.46
    jint
    -0.44
    uric
    -0.43
    inty
    -0.42
    ac
    -0.40
    ,
    -0.39
    orte
    -0.39
    Du
    -0.39
    ede
    -0.39
    lat
    -0.39
    POSITIVE LOGITS
    <bos>
    3.03
     Савезне
    1.23
    ’
    1.13
    '
    1.11
     Paglinawan
    1.11
     disambiguazione
    1.08
    хьтан
    1.07
     виправивши
    1.02
     فريبيس
    1.01
     мәкал
    0.96
    Activations Density 0.948%

    No Known Activations